NCJ Number
65177
Journal
Evaluation Review Volume: 4 Issue: 1 Dated: (FEBRUARY 1980) Pages: 5-41
Date Published
1980
Length
37 pages
Annotation
A METHOD FOR MONITORING SUBJECTIVE INDICATORS OVER DIFFERENT DEMOGRAPHIC SEGMENTS AND TIME POINTS IS PRESENTED, BASED ON PSYCHOMETRIC SCALING THEORY.
Abstract
THE GOAL OF THE MODEL IS TO CORRECT THE IMBALANCE IN SOCIAL INDICATORS WORK RESULTING FROM THE DOMINANCE OF 'OBJECTIVE' MEASURES EXPRESSED IN VARIOUS PHYSICAL UNITS (I.E., CRIME RATES). MUCH CURRENT DISCUSSION FOCUSES ON THE CONCEPT OF LIFE QUALITY, WHICH IS BASED ON SUBJECTIVE VARIABLES. THE PRESENT MONITORING MODEL IS SIMILAR TO MODELS IN TEST AND CHOICE THEORY AND REPRESENTS A GENERALIZATION OF SUCCESSIVE INTERVALS SCALING THEORY. ITS PARAMETERS ARE ESTIMATED NONITERATIVELY. THE MODEL IS DESCRIBED FOR THE TWO-PARAMETER, ERRORLESS CASE AND FOR CASES IN WHICH THERE ARE SAMPLING ERRORS. NEXT, THE MODEL IS ESTIMATED AND FITTED. THE MODEL'S MAIN ADVANTAGE, WHEN APPLIED TO SURVEY RATING SCALES, STEMS FROM BUILT-IN PARAMETERS WHICH PROVIDE FOR ITS EVALUATION. THIS EVALUATION YIELDS ENCOURAGING RESULTS IN THE MODEL'S APPLICATIONS TO CROSS-CLASSIFIED SURVEY DATA. USING DATA FROM THREE NATIONAL SURVEYS OF INCOME AND LIFE SATISFACTION, THE MODEL SHOWED THAT SATISFACTION WITH FAMILY INCOME AND STANDARD OF LIVING INCREASES MONOTONICALLY WITH ACTUAL INCOME IN EACH OF THE SURVEYS. DRAWING ON TWO NATIONAL SURVEYS OF CONSUMER SATISFACTION, THE MODEL SHOWED CONSISTENT LEVELS OF CONSUMER SATISFACTION WITH DAIRY PRODUCTS AND EGGS, BAKERY AND CEREAL PRODUCTS, AND PROCESSED FRUITS AND VEGETABLES, AS WELL AS A LOW LEVEL OF SATISFACTION WITH THE RELIABILITY OF INFORMATION IN ADVERTISEMENTS SPONSORED BY FOOD MANUFACTURERS. DATA ALSO SHOWED INCREASING VARIATION AMONG SATISFACTION VALUES WITH INCREASING INCOME LEVEL. IN ADDITION TO THESE PASSIVE APPLICATIONS, THE MODEL CAN BE USED IN FIELD STUDIES INVOLVING QUASI-EXPERIMENTAL DESIGN, WITH EXPERIMENTAL GROUPS, CONTROL GROUPS, AND COMPARISONS BEFORE AND AFTER AN IMPOSED TREATMENT. OTHER APPLICATIONS INCLUDE SIMILARITY SCALING AND CONSTRUCTION OF FACTORIAL QUESTIONNAIRES. TABLES, NOTES, AN APPENDIX GIVING DETAILS OF THE METHOD, AND BIBLIOGRAPHY ARE INCLUDED. (CFW)